正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Thats awesome! A developer used Al-powered 4D Gaussian Splatting to convert flat video footage into dynamic 3D spatial scenes. The system reconstructs different camera angles and depth information from ordinary footage, making it possible to navigate scenes in three dimensions. We're moving from recording video to digitally recreating reality itself.

SciTech Era

22,701 subscribers

73,730 次观看 • 4 个月前 •via X (Twitter)

艺术教育科学技术

Anya Rossi• Live Now

Private livecam show

26 条评论

SciTech Era 的头像

SciTech Era4 个月前

if you wanna read: source of above video:

𓂀 PARALLAX ᯅ 🇪🇺 Fuck right wing bigots🇵🇸 的头像

𓂀 PARALLAX ᯅ 🇪🇺 Fuck right wing bigots🇵🇸4 个月前

Wishful thinking. From the page you’re linking to, which is not project but an explanation of 4DGS. It’s not based on one 2D video stream…

packet ears 的头像

packet ears4 个月前

finally a reason to upgrade a computer cpu with a gpu & npu. imagine watching a movie, then using such a technology to change your pov whenever you want to, while the movie continues to play at it's usual 24fps.

田中義弘 | taziku CEO / AI × Creative 的头像

田中義弘 | taziku CEO / AI × Creative4 个月前

動画を「再利用できる空間データ」として扱えるようになるのが大きいですね。既存映像から体験型コンテンツへ変換するワークフローが生まれそう。

Tirius99 的头像

Tirius994 个月前

One step closer to the Holodeck

Elson 的头像

Elson4 个月前

This is amazing lol

Stellarix 的头像

Stellarix4 个月前

Gaussian splatting combined with AI can reconstruct spatial depth and multiple viewpoints from ordinary video footage. These advances in neural rendering and volumetric reconstruction are pushing digital media beyond flat recording toward immersive, navigable representations of real-world environments.

Andrew Holdun 的头像

Andrew Holdun4 个月前

Zapruder film to 3D anyone? Latest UFO Pentagon Video?

Suran Goonatilake 的头像

Suran Goonatilake4 个月前

Nonsense. Can’t be done, yet.

Diego 的头像

Diego4 个月前

this.

XRWorld 的头像

XRWorld4 个月前

its fake. of you want to watch imagined angles do it. i dont

币猎.eth🐑 的头像

币猎.eth🐑4 个月前

source: paper?

米粒的头像

米粒4 个月前

太強了👍

kevin¹ 的头像

kevin¹4 个月前

How to call this? 4DGS ?

williamchen 的头像

williamchen4 个月前

4D Gaussian Splatting sounds like sci-fi jargon but the result is pure magic. Can't wait to see this in games or VR tours.

Dungeon Fox 的头像

Dungeon Fox4 个月前

oh hey I use a similar technique though when correct it should function with far greater detail. (based on holographics)

Ben Dunaway 的头像

Ben Dunaway4 个月前

That’s very cool!

Cell Knights: TD → Demo Out Now!🔥 的头像

Cell Knights: TD → Demo Out Now!🔥4 个月前

Now harry potter is real?

iman₿oer 的头像

iman₿oer4 个月前

wow thats big 👏🏼👏🏼👏🏼 so you can see every angle from any movie? 🫣

EasyClaw 的头像

EasyClaw4 个月前

2D video → 3D spatial scene. That’s not just rendering. That’s reconstructing reality. Now imagine the same leap for workflows: → Flat task description → Dynamic agent execution across tools, files, and APIs → Full spatial awareness of your digital environment That’s @EasyClaw. We’re moving from recording instructions to digitally executing work itself. Same leap. Different dimension. ⚡️

Starkium 的头像

Starkium4 个月前

this is probably the worst version of this I've seen

Sweatt-JoJo 的头像

Sweatt-JoJo4 个月前

Good job 👏

Olivia 的头像

Olivia4 个月前

wow amazing

Ethan Walker 的头像

Ethan Walker4 个月前

4DGS addresses the missing piece: scanning existing infrastructure into spatial formats at scale. Makes Omniverse workflows viable for real-world deployment.

Wanderer of the Stars 的头像

Wanderer of the Stars4 个月前

I suspect the porn industry is already claiming dibs on this. 😂

takeyourmeds 的头像

takeyourmeds4 个月前

>no vertical rotation ngmi

相关视频

🤖 wake up, new 4d tool! Take any normal 2D video → instantly turn it into fully explorable 3D space. You can now orbit, tilt, and view the scene from angles that literally never existed in the original footage. This is 4D Gaussian Splatting (from 4dv) and it’s next-level.

🤖 wake up, new 4d tool! Take any normal 2D video → instantly turn it into fully explorable 3D space. You can now orbit, tilt, and view the scene from angles that literally never existed in the original footage. This is 4D Gaussian Splatting (from 4dv) and it’s next-level.

filipe

66,514 次观看 • 4 个月前

🇺🇸 Insta360 Spatial Capture is officially coming to the U.S. on Sep. 28! Update the Insta360 app to the latest version (2.34.0) via your mobile app store or download it from our website, and experience Spatial Capture with Insta360 X4 Air, X5, and X6. Powered by 3D Gaussian Splatting, Spatial Capture lets you scan a room or object with a 360 video and turn it into a fully explorable 3D model—all directly in the Insta360 app. With high quality imaging and native 360 video recording, Insta360 cameras make 3D Gaussian Splatting scanning more accessible, so it's easier than ever to capture and preserve your memories in an immersive 3D format.

🇺🇸 Insta360 Spatial Capture is officially coming to the U.S. on Sep. 28! Update the Insta360 app to the latest version (2.34.0) via your mobile app store or download it from our website, and experience Spatial Capture with Insta360 X4 Air, X5, and X6. Powered by 3D Gaussian Splatting, Spatial Capture lets you scan a room or object with a 360 video and turn it into a fully explorable 3D model—all directly in the Insta360 app. With high quality imaging and native 360 video recording, Insta360 cameras make 3D Gaussian Splatting scanning more accessible, so it's easier than ever to capture and preserve your memories in an immersive 3D format.

Insta360

66,224 次观看 • 10 天前

Here is some new footage from this paper, offering a glimpse into the future of dynamic 3D Gaussian Splatting models combined with static reconstructed scenes. Imagine this: when the lighting matches, the result becomes practically indistinguishable from reality. Just pick a scene, add characters, and record it from any angle. Apply diffusion models to instantly change the look. I firmly believe this is the future of VFX.

Here is some new footage from this paper, offering a glimpse into the future of dynamic 3D Gaussian Splatting models combined with static reconstructed scenes. Imagine this: when the lighting matches, the result becomes practically indistinguishable from reality. Just pick a scene, add characters, and record it from any angle. Apply diffusion models to instantly change the look. I firmly believe this is the future of VFX.

MrNeRF

58,210 次观看 • 10 个月前

A video is compressed 4D data. 🌍 Today, we’re sharing a preview of our latest research: 4D reconstruction from a single monocular video. 🎬 From one casually captured video, our system reconstructs a dynamic, freely viewable 4D Gaussian scene—recovering geometry, appearance, camera motion, and object motion across space and time. No multi-camera rig. Just video → 4DGS. The world has already been captured in video. The next step is to unlock the 4D structure inside it. Watch the result below. 👇 #4DGS #GaussianSplatting #CVPR #CVPR2026 #AIGC #AI #3DGS

A video is compressed 4D data. 🌍 Today, we’re sharing a preview of our latest research: 4D reconstruction from a single monocular video. 🎬 From one casually captured video, our system reconstructs a dynamic, freely viewable 4D Gaussian scene—recovering geometry, appearance, camera motion, and object motion across space and time. No multi-camera rig. Just video → 4DGS. The world has already been captured in video. The next step is to unlock the 4D structure inside it. Watch the result below. 👇 #4DGS #GaussianSplatting #CVPR #CVPR2026 #AIGC #AI #3DGS

InSpatio｜影溯

64,567 次观看 • 2 个月前

4D videos, are we cooked? 😳 uses 4D Gaussian Splatting to reconstruct real footage into fully explorable scenes, letting you move the camera freely through a moment after it’s been filmed. Combine it with tools like Seedance for character replacement and motion control, and Beeble for relighting, and you unlock entire cinematic workflows. You can even step inside your scenes in augmented reality with the Apple Vision Pro. #4DVAI #GaussianSplatting #AIVideoWorkflow #CreativeAI #SpatialVideo

4D videos, are we cooked? 😳 uses 4D Gaussian Splatting to reconstruct real footage into fully explorable scenes, letting you move the camera freely through a moment after it’s been filmed. Combine it with tools like Seedance for character replacement and motion control, and Beeble for relighting, and you unlock entire cinematic workflows. You can even step inside your scenes in augmented reality with the Apple Vision Pro. #4DVAI #GaussianSplatting #AIVideoWorkflow #CreativeAI #SpatialVideo

Rourke Heath

69,783 次观看 • 2 个月前

This will change how sports content gets made and delivered. The method is Gaussian splatting. It takes video from multiple camera positions and rebuilds the whole thing in three dimensions, viewable from any angle. Instead of polygons (the way games render), it builds the scene from millions of tiny glowing splats of color and depth. Arcturus runs it across time (4D), so a live game becomes a 3D scene, shown from field level, beside a player, or above the play.

This will change how sports content gets made and delivered. The method is Gaussian splatting. It takes video from multiple camera positions and rebuilds the whole thing in three dimensions, viewable from any angle. Instead of polygons (the way games render), it builds the scene from millions of tiny glowing splats of color and depth. Arcturus runs it across time (4D), so a live game becomes a 3D scene, shown from field level, beside a player, or above the play.

James Morrison Rubin

68,906 次观看 • 27 天前

Introducing 👀Stereo4D👀 A method for mining 4D from internet stereo videos. It enables large-scale, high-quality, dynamic, *metric* 3D reconstructions, with camera poses and long-term 3D motion trajectories. We used Stereo4D to make a dataset of over 100k real-world 4D scenes.

Introducing 👀Stereo4D👀 A method for mining 4D from internet stereo videos. It enables large-scale, high-quality, dynamic, metric 3D reconstructions, with camera poses and long-term 3D motion trajectories. We used Stereo4D to make a dataset of over 100k real-world 4D scenes.

Linyi Jin

94,683 次观看 • 1 年前

More and more users are turning their 360 footage into fully explorable 3D Gaussian Splats with View it here: This reconstruction started from a simple capture and is now a fully explorable 3D Gaussian Splat rendered in the FreeGaussian viewer, complete with point cloud reconstruction and high-fidelity spatial detail. More and more creators are discovering that their existing footage can become immersive 3D scenes. And they’re doing it for free with FreeGaussian

More and more users are turning their 360 footage into fully explorable 3D Gaussian Splats with View it here: This reconstruction started from a simple capture and is now a fully explorable 3D Gaussian Splat rendered in the FreeGaussian viewer, complete with point cloud reconstruction and high-fidelity spatial detail. More and more creators are discovering that their existing footage can become immersive 3D scenes. And they’re doing it for free with FreeGaussian

Over the Reality 🌐

14,829 次观看 • 4 个月前

We’ve upgraded Stable Video Diffusion 4D to Stable Video 4D 2.0 (SV4D 2.0), improving the quality of 4D outputs generated from a single object-centric video. While 3D provides a static view of an object’s shape and size; 4D extends this by including time, showing how the object moves. This multi-view video diffusion model generates a 4D output in three steps: 1️⃣ Starts with an input video of a moving person or object 2️⃣ Generates novel views of the subject from unseen angles 3️⃣ Constructs a single dynamic 4D video output with spatial and temporal consistency You can learn more here: (1/4)

We’ve upgraded Stable Video Diffusion 4D to Stable Video 4D 2.0 (SV4D 2.0), improving the quality of 4D outputs generated from a single object-centric video. While 3D provides a static view of an object’s shape and size; 4D extends this by including time, showing how the object moves. This multi-view video diffusion model generates a 4D output in three steps: 1️⃣ Starts with an input video of a moving person or object 2️⃣ Generates novel views of the subject from unseen angles 3️⃣ Constructs a single dynamic 4D video output with spatial and temporal consistency You can learn more here: (1/4)

Stability AI

36,059 次观看 • 1 年前

Gaussian splats in Blender 5.3! Had to take it for a quick spin ofc - here with a scene I did using a generated image, Minimax H3-Max camera control through - converted to Gaussian splats with KIRI Engine - 3D Scanner App. It is possible to relight scenes with Gaussian Splats too, but it was pretty sloggish for me, even on a 5090. Could probably get better results with some optimization. It is kinda crazy to see this unfold - from image, to video, to 3d to dynamic generative worlds.

Gaussian splats in Blender 5.3! Had to take it for a quick spin ofc - here with a scene I did using a generated image, Minimax H3-Max camera control through - converted to Gaussian splats with KIRI Engine - 3D Scanner App. It is possible to relight scenes with Gaussian Splats too, but it was pretty sloggish for me, even on a 5090. Could probably get better results with some optimization. It is kinda crazy to see this unfold - from image, to video, to 3d to dynamic generative worlds.

Martin Nebelong

22,516 次观看 • 6 天前

⚡Say hello to Wonder Animation⚡ - Kickstart your animated project with groundbreaking Video to 3D Scene technology. Convert live footage into 3D scenes with all camera setups, character body and face animation, and fully editable elements in one 3D space. Discover your next level of creativity today! 👉Learn more: #Animation #3D #WonderStudio #WonderDynamics

⚡Say hello to Wonder Animation⚡ - Kickstart your animated project with groundbreaking Video to 3D Scene technology. Convert live footage into 3D scenes with all camera setups, character body and face animation, and fully editable elements in one 3D space. Discover your next level of creativity today! 👉Learn more: #Animation #3D #WonderStudio #WonderDynamics

Autodesk Flow Studio

349,755 次观看 • 1 年前

From 2D video to a very rough 4D Gaussian Splatting POC on the Apple Vision Pro 👀 Took Big Buck Bunny frames, turned them into Gaussian splats with Sharp (Apple), compressed them with PlayCanvas splat transform to SOG, and played all frames via WebXR + spark Still rough and not fully optimized, but wow, dynamic GS in AVP feels wild 🤯 Second part of the video is on my laptop #threejs

From 2D video to a very rough 4D Gaussian Splatting POC on the Apple Vision Pro 👀 Took Big Buck Bunny frames, turned them into Gaussian splats with Sharp (Apple), compressed them with PlayCanvas splat transform to SOG, and played all frames via WebXR + spark Still rough and not fully optimized, but wow, dynamic GS in AVP feels wild 🤯 Second part of the video is on my laptop #threejs

Stijn Spanhove

20,258 次观看 • 9 个月前

🏗️ Applied Showcase: Photorealistic 3D scenes from video, running entirely in your browser. Gauzilla Pro (Gauzilla Pro) turns drone and smartphone footage into navigable digital twins with AI-powered segmentation. The platform runs on WebAssembly with no CUDA or Python installs. The core renderer is open-source Rust if you want to see how the splatting math actually works. 🔗 #GaussianSplatting #DigitalTwins #WebAssembly #3DReconstruction #AEC

🏗️ Applied Showcase: Photorealistic 3D scenes from video, running entirely in your browser. Gauzilla Pro (Gauzilla Pro) turns drone and smartphone footage into navigable digital twins with AI-powered segmentation. The platform runs on WebAssembly with no CUDA or Python installs. The core renderer is open-source Rust if you want to see how the splatting math actually works. 🔗 #GaussianSplatting #DigitalTwins #WebAssembly #3DReconstruction #AEC

WebGL / WebGPU

18,677 次观看 • 8 个月前

Introducing powered by Over the Reality. FreeGaussian is a new way to transform your existing photos, videos, and 360 captures for free into high-quality 3D Gaussian splats, directly in your browser. Whether you already have: ↳ a 360 recording captured with any 360 camera ↳ a set of photos ↳ or even a simple video from a place you visited you can now turn it into a photorealistic 3D Gaussian splat. Just go to upload your content, and let the reconstruction happen. Once it’s ready, you can download your 3D Gaussian splat and point cloud, and use them across your own projects, pipelines, or applications.

Introducing powered by Over the Reality. FreeGaussian is a new way to transform your existing photos, videos, and 360 captures for free into high-quality 3D Gaussian splats, directly in your browser. Whether you already have: ↳ a 360 recording captured with any 360 camera ↳ a set of photos ↳ or even a simple video from a place you visited you can now turn it into a photorealistic 3D Gaussian splat. Just go to upload your content, and let the reconstruction happen. Once it’s ready, you can download your 3D Gaussian splat and point cloud, and use them across your own projects, pipelines, or applications.

Over the Reality 🌐

86,340 次观看 • 5 个月前

Gaussian Garments: Reconstructing Simulation-Ready Clothing with Photorealistic Appearance from Multi-View Video Contribution quote from the paper: In summary, our main contributions are • a comprehensive pipeline for reconstructing the shape, appearance, and behavior of real-world garments using Gaussian splatting, • an algorithm for registering garment meshes to multi- view videos with an optimization procedure based on Gaussian splatting, and • a Gaussian Garment representation that combines triangle meshes with Gaussian textures to capture photorealistic appearance and can be used as a fully controllable 3D asset.

Gaussian Garments: Reconstructing Simulation-Ready Clothing with Photorealistic Appearance from Multi-View Video Contribution quote from the paper: In summary, our main contributions are • a comprehensive pipeline for reconstructing the shape, appearance, and behavior of real-world garments using Gaussian splatting, • an algorithm for registering garment meshes to multi- view videos with an optimization procedure based on Gaussian splatting, and • a Gaussian Garment representation that combines triangle meshes with Gaussian textures to capture photorealistic appearance and can be used as a fully controllable 3D asset.

MrNeRF

27,354 次观看 • 2 年前

Celebrating 25 Years of That’s the Way It Is! To mark this milestone, we’re thrilled to share this rare footage from the making of this iconic music video. Witness the magic behind the scenes and relive the moments that made history. ✨ Dive into the magic: P.S. Don’t forget to watch the official video, it’s now in HD!

Celebrating 25 Years of That’s the Way It Is! To mark this milestone, we’re thrilled to share this rare footage from the making of this iconic music video. Witness the magic behind the scenes and relive the moments that made history. ✨ Dive into the magic: P.S. Don’t forget to watch the official video, it’s now in HD!

Celine Dion

61,511 次观看 • 1 年前

Robot Learning needs 4D world models! Robot Learning needs 4D world models! Robot Learning needs 4D world models! We introduce TesserAct, a 4D embodied world model that can simulate how agents interact with the 3D world over time! We achieve this by simply extending a pre-trained 2D video generation model to jointly predict RGB, depth, and surface normals. It enables: 1️⃣ Much better policy learning in the wild 2️⃣ Temporal + spatial coherence in 4D dynamic prediction 3️⃣ Novel view synthesis for embodied scenes Code: Paper Link: Project page:

Robot Learning needs 4D world models! Robot Learning needs 4D world models! Robot Learning needs 4D world models! We introduce TesserAct, a 4D embodied world model that can simulate how agents interact with the 3D world over time! We achieve this by simply extending a pre-trained 2D video generation model to jointly predict RGB, depth, and surface normals. It enables: 1️⃣ Much better policy learning in the wild 2️⃣ Temporal + spatial coherence in 4D dynamic prediction 3️⃣ Novel view synthesis for embodied scenes Code: Paper Link: Project page:

Chuang Gan

43,265 次观看 • 1 年前

GPS-Gaussian+: Generalizable Pixel-wise 3D Gaussian Splatting for Real-Time Human-Scene Rendering from Sparse Views TL;DR: Are we witnessing the first steps towards 3DGS live streaming? Contributions: • We introduce a generalizable 3D Gaussian Splatting methodology that employs pixel-wise Gaussian parameter maps defined on 2D source image planes to formulate 3D Gaussians in a feed-forward manner. • We propose a fully differentiable framework composed of an iterative depth estimation module and a Gaussian parameter regression module. The intermediate depth prediction bridges the two components and allows them to benefit from joint training. • We introduce a regularization term and an epipolar attention mechanism to preserve geometry consistency between the two source views when using only rendering loss. Our method generalizes well to unseen characters even in complicated scenes. • We develop a real-time FVV system that achieves high-resolution rendering of characters in the scene without any geometry supervision.

GPS-Gaussian+: Generalizable Pixel-wise 3D Gaussian Splatting for Real-Time Human-Scene Rendering from Sparse Views TL;DR: Are we witnessing the first steps towards 3DGS live streaming? Contributions: • We introduce a generalizable 3D Gaussian Splatting methodology that employs pixel-wise Gaussian parameter maps defined on 2D source image planes to formulate 3D Gaussians in a feed-forward manner. • We propose a fully differentiable framework composed of an iterative depth estimation module and a Gaussian parameter regression module. The intermediate depth prediction bridges the two components and allows them to benefit from joint training. • We introduce a regularization term and an epipolar attention mechanism to preserve geometry consistency between the two source views when using only rendering loss. Our method generalizes well to unseen characters even in complicated scenes. • We develop a real-time FVV system that achieves high-resolution rendering of characters in the scene without any geometry supervision.

MrNeRF

25,893 次观看 • 1 年前

Our new Gaussian point splatting renders huge 3DGS scenes in real time (e.g. 425 M⬇️). It samples pixel-sized points from the Gaussians with massive parallelism and splats them to the screen using 64-bit atomics. Grab ACM SIGGRAPH 2026 paper+code+video now:

Our new Gaussian point splatting renders huge 3DGS scenes in real time (e.g. 425 M⬇️). It samples pixel-sized points from the Gaussians with massive parallelism and splats them to the screen using 64-bit atomics. Grab ACM SIGGRAPH 2026 paper+code+video now:

Christoph Peters

23,287 次观看 • 4 个月前

Runway Aleph is a new way to edit, transform and generate video. Its ability to perform a wide range of generalized tasks means it can reimagine ordinary footage in endless new ways. Allowing you to turn images and videos you already have into anything you want. See below for a quick breakdown on how Aleph can effortlessly remove the subject from these scenes, just by asking it to.

Runway Aleph is a new way to edit, transform and generate video. Its ability to perform a wide range of generalized tasks means it can reimagine ordinary footage in endless new ways. Allowing you to turn images and videos you already have into anything you want. See below for a quick breakdown on how Aleph can effortlessly remove the subject from these scenes, just by asking it to.

Runway

37,873 次观看 • 1 年前